[Explainable artificial intelligence in pathology].

Journal: Pathologie (Heidelberg, Germany)
PMID: 38315198

Abstract

With the advancements in precision medicine, the demands on pathological diagnostics have increased, requiring standardized, quantitative, and integrated assessments of histomorphological and molecular pathological data. Great hopes are placed in artificial intelligence (AI) methods, which have demonstrated the ability to analyze complex clinical, histological, and molecular data for disease classification, biomarker quantification, and prognosis estimation. This paper provides an overview of the latest developments in pathology AI, discusses the limitations, particularly concerning the black box character of AI, and describes solutions to make decision processes more transparent using methods of so-called explainable AI (XAI).

Authors

  • Frederick Klauschen
    Pathologisches Institut, Ludwig-Maximilians-Universität München, Thalkirchner Str. 36, 80337, München, Deutschland. f.klauschen@lmu.de.
  • Jonas Dippel
    Machine Learning Group, Technische Universität Berlin, Berlin, Deutschland.
  • Philipp Keyl
    Institute of Pathology, Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin and Humboldt-Universität Berlin, Charitéplatz 1, 10117 Berlin, Germany.
  • Philipp Jurmeister
    Institute of Pathology, Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin, Humboldt-Universität zu Berlin and Berlin Institute of Health, 10117 Berlin, Germany.
  • Michael Bockmayr
    Institute of Pathology, Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin, Humboldt-Universität zu Berlin and Berlin Institute of Health, 10117 Berlin, Germany.
  • Andreas Mock
    Department of Translational Medical Oncology (TMO), National Center for Tumor Diseases (NCT) Heidelberg, German Cancer Research Center (DKFZ) Heidelberg, Im Neuenheimer Feld 460, 69120 Heidelberg, Germany.
  • Oliver Buchstab
    Institute of Pathology, Ludwig-Maximilians-Universität München, Munich, Germany; email: f.klauschen@lmu.de.
  • Maximilian Alber
    Berlin Big Data Center, Berlin Institute of Technology, Berlin, Germany.
  • Lukas Ruff
    Aignostics, Berlin, Germany.
  • Grégoire Montavon
    Machine Learning Group, Technische Universität Berlin, Berlin, Germany.
  • Klaus-Robert Müller
    Berlin Institute for the Foundations of Learning and Data (BIFOLD), Berlin, Deutschland.

Keywords

External Resources

Popular Topics
Recent Journals